The web ad-click fraud detection approach for supporting to the online advertising system
by Pankaj Kumar Keserwani; Mahesh Chandra Govil; Emmanuel Shubhakar Pilli
International Journal of Swarm Intelligence (IJSI), Vol. 7, No. 1, 2022

Abstract: With the introduction of e-commercial activities, revenue is generated in several legal and illegal ways. Marketing of a product or service in an online environment is increasing day by day since most users are getting involved in an online environment for buying or selling items. As a result, attackers are getting more space for performing online attacks by different malicious activities. The advertisement (ad) fraud, which is increasing exponentially with each passing day, is one of them. Ad fraud causes defame for the online advertising system and low return on the advertiser's investment (ROI). The paper reveals a methodology for detecting web ad-click frauds so that the ROI of an advertiser can be increased. The developed algorithm to detect the ad-click frauds in the proposed methodology can detect the web ad-click frauds. The results of the ad-click fraud algorithm are verified with the help of popular machine learning (ML) algorithms - k-nearest neighbour (k-NN), random forest (RF), decision tree (DT), logistic regression (LR) and support vector machine (SVM), with accuracies achieved.

Online publication date: Thu, 24-Feb-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Swarm Intelligence (IJSI):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email